I've been in a similar situation as the GP. 15 years ago my first job after college was at a large Fortune 500 building LOB apps. The company was full of departments that were run entirely out of a massive Excel spreadsheet (hundreds of MB or more), or better yet a totally custom thing built on Access97 and VB made by a guy who retired 10 years ago. More than a few of the people in these departments had been in the same job for 20+ years and literally done the job the same way the whole time. Our mandate was not to modernize their business processes or make them friendly to automation, it was literally to indulge their stupid whims. But at least at the end they would be on an app where IT had access to the source code, could ensure databases were backed up, etc.
I'm curious how much value others are finding in this. Personally I turned it off about a year ago and went back to traditional (jetbrains) IDE autocomplete. In my experience the AI suggestions would predict exactly what I wanted < 1% of the time, were useful perhaps 10% of the time, and otherwise were simply wrong and annoying. Standard IDE features allowing me to quickly search and/or browse methods, variables, etc. are far more useful for translating my thoughts into code (i.e. minimizing typing).
Same, I use Claude but cannot stand typing and being constantly flashed with suggestions that aren't right and have to keep hitting escape to cancel them. It's either manual or full AI for me. This happens in a lot if web tools that have been enhanced with AI, like a few databases with web UIs that allow querying. They are so bad. I really wish they would just dump the whole schema into the context before I begin because I don't need fancy autocomplete, I need schema, table, and column autocomplete wayyy more than I need it to scaffold out a SELECT for me.
I have it on a long timer so that I have to pause for a while before the auto-complete prompt appears. I've found I tend to deliberately set things up for it to attempt when I know I'm going to have to type a bunch of boiler plate or some code that's logically straightforward but syntactically fiddly ie. I write a quick comment describing what the next few lines should do and then wait a seconds for it to make the suggestion
Can't speak for intelligent autocomplete writ large, but I treat it as an ergonomic feature, and Cursor's implementation is pretty good (though I'm not sure it's improved all that much in the past year).
It constantly takes whatever is currently visible in your editor to feed its context. If you get a nonsense/hallucinated suggestion, you can accept it, get it to read the error message from LSP diagnostics, undo, and then it'll correct itself next time. Or if you need to make changes in 5 places, and the next 4 changes are easy to guess after seeing the first one, it'll guess the next 4 for you.
I still use standard IDE features extensively. The intelligent autocomplete is just another tool to reduce typing when the next change is easy to guess.
Oh, and I turn it off when I'm writing prose or need to actually think deeply. Then it really does hurt more then help.
(Worth noting: I currently work primarily in Go, which is a language that's ridiculously verbose and has lots of repetitive patterns. YMMV for more expressive languages.)
Even worse, I've seen the JetBrains AI auto-complete insert hard-to-spot bugs, like two nested for loops with i and j for loop index variables, where the inner loop was fairly complex and incorrectly used i instead of j in one place.
perhaps it depends on language or domain but for me it's usually a minimum of 50% but often 80% what in looking for (lots of web off like typescript, svelte, cloudflare workers, tailwind etc).
Definitely have mixed feelings about whats become of CNN and how the 24 hour news cycle has affected the world, but I'm very grateful that Turner financed the movie Gettysburg [0]. One of my favorite movies, based on one of my favorite books. I've probably seen it at least 50 times.
I had a TI-83 in high school and upgraded to a TI-89 for college circa 2002. Used the heck out of those calculators because I did all the math and physics prerequisites for an engineering degree before switching to CS. It also helped me get a B in Linear Algebra thanks to holding a cheat sheet document for the final exam. I had no trouble with the likes of Calculus 3 and differential equations but for some reason the later material in linear algebra didn't click with me.
That's not quite accurate. They have 10 days to issue you a temporary credit if the investigation is going to take more than 10 days. They are willing to issue the credit immediately precisely because it's temporary. If the investigation resolves in your favor the credit becomes permanent and you never know the difference. If it takes more than 30 days - well, I worked with BofA about 15 years ago and saw more than a few customers who ended up with a giant mess because that temporary credit expired after 30 days resulting in a snowball effect of failed payments and NSF charges.
I've been using it for a few months because Copilot was the only AI blessed by our corporate overlords. It's not bad, I would say it's about 80% as capable as Claude Code, which I've used extensively on personal projects. However CC was recently approved, and I'm betting that with these changes to Copilot pricing we'll end up dropping it like a hot potato.
If you're suggesting that the US submarine should have rescued the survivors - with respect I think you don't understand how submarines work. They have no capability to perform rescue operations. They have no way to handle mass numbers of injuries, there's normally just one corpsman (basically a medic) on board. Even if they want to do a rescue operation they have no place to put them. Subs barely have room for their own crew; typically 2 or even 3 sailors share the same bed.
There was zero threat to that American submarine, they fired on an unarmed ship that the US Navy had just held ceremonial activities with literally days prior. Absolutely disgusting behaviour but we can't expect anything less from the Americans unfortunately.
Modern subs don't run on the surface routinely like WWII subs did. Practically all they could do would be float some life boats up, but they were probably >10 nm away, so it wouldn't have been in position to deliver them promptly.
The situation with the ambulance service is obviously disgusting and immoral in a civilized society. But the article fails to address the elephant in the room - her chief complaint was severe pain in her knees due to RA. If she had been taken to the ER she almost certainly would've been given some short term pain meds and sent home unless she was showing some very obvious signs of cardiac issues. The system had already failed her because she really needed skilled nursing or assisted living help, being immobile due to chronic disease. It happens all the time. Several years ago my elderly father fractured an ankle - no surgery required, just a boot - and was sent home even though he was unable to stand or walk on his own. Fortunately he had savings and I was able to talk him into paying out of pocket for a stay in rehab (to the tune of about $18,000).
It's also likely that she ended up in this position because she couldn't afford proper treatment of her RA, resulting in it destroying her knees. I also have RA, diagnosed 3 years ago and my treatment costs $15,000 per month. Losing my job and/or having insurance that won't cover it is a terror that knaws at the back of my mind because without the treatment I'll start suffering debilitating symptoms in 3-6 months.
Well, unfortunately there's a herd of elephants in the room when it comes to American healthcare.
We spend the most on healthcare vs any other nation while getting results comparable to nations like Cuba (not hyperbole. Go look up infant mortality of Cuba vs US). I mean, no joke, the main thing that harms Cuban healthcare is the US embargo limiting medicine and medical supplies from going in.
An awful lot of corporate workers are stuck with Copilot as their only approved chat option, so some of them are probably trying to learn how to get the best results they can from it.
I've been working off and on on a vibe coded FP language and transpiler - mostly just to get more experience with Claude Code and see how it handles complex real world projects. I've settled on a very similar flow, though I use three documents: plan, context, task list. Multiple rounds of iteration when planning a feature. After completion, have a clean session do an audit to confirm that everything was implemented per the design. Then I have both Claude and CodeRabbit do code review passes before I finally do manual review. VERY heavy emphasis on tests, the project currently has 2x more test code than application code. So far it works surprisingly well. Example planning docs below -
reply